© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 10729
    Prev
    Next
    INDEX
    Explanations

    the word "see" and words associated with sensing something, like "hear"

    oai_token-act-pair · gemini-2.0-flash

    senses

    np_max-act · gemini-2.0-flash

    ▁see

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     "..\..\
    -0.80
     "..\..\..\
    -0.70
     ویکی‌پدی
    -0.70
    InitVars
    -0.69
    تقاوى
    -0.69
     ddelweddau
    -0.67
    :+:
    -0.65
     Efq
    -0.62
    脚注の使い方
    -0.60
     NSCoder
    -0.60
    POSITIVE LOGITS
     across
    0.53
    tifact
    0.51
    npos
    0.50
    <bos>
    0.48
    яна
    0.47
    fxml
    0.47
     within
    0.46
    Voci
    0.46
     get
    0.46
    addGap
    0.45
    Activations Density 0.276%

    No Known Activations